ViCLIP-OT: The First Foundation Vision-Language Model for Vietnamese Image-Text Retrieval with Optimal Transport

Quoc-Khang Tran, Minh-Thien Nguyen, Nguyen-Khang Pham · Feb 26, 2026 · Citations: 0

Abstract

Image-text retrieval has become a fundamental component in intelligent multimedia systems; however, most existing vision-language models are optimized for highresource languages and remain suboptimal for low-resource settings such as Vietnamese. This work introduces ViCLIP-OT, a foundation vision-language model specifically designed for Vietnamese image-text retrieval. The proposed framework integrates CLIP-style contrastive learning with a Similarity-Graph Regularized Optimal Transport (SIGROT) loss to enhance global cross-modal consistency and mitigate modality gap issues. Extensive experiments on three Vietnamese benchmarks (UITOpenViIC, KTVIC, and Crossmodal-3600) demonstrate that ViCLIP-OT consistently outperforms CLIP and SigLIP baselines in both in-domain and zero-shot settings. On UIT-OpenViIC, the model achieves an average Recall@K of 67.34%, improving upon CLIP by 5.75 percentage points. In zero-shot evaluation on Crossmodal-3600, ViCLIPOT surpasses CLIP by 11.72 percentage points. Embedding-space analysis further confirms improved alignment and reduced modality gap. The results indicate that integrating SIGROT provides an effective and scalable strategy for cross-modal retrieval in low-resource languages, offering practical implications for intelligent multimedia retrieval systems in Vietnamese and other underrepresented linguistic contexts.

HFEPX Relevance Assessment

This paper appears adjacent to HFEPX scope (human-feedback/eval), but does not show strong direct protocol evidence in metadata/abstract.

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Human Data Lens

Uses human feedback: No
Feedback types: None
Rater population: Unknown
Unit of annotation: Unknown
Expertise required: General
Extraction source: Runtime deterministic fallback

Evaluation Lens

Evaluation modes: Automatic Metrics
Agentic eval: None
Quality controls: Not reported
Confidence: 0.35
Flags: low_signal, possible_false_positive, runtime_fallback_extraction

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

recallrecall@k

Research Brief

Deterministic synthesis

Extensive experiments on three Vietnamese benchmarks (UITOpenViIC, KTVIC, and Crossmodal-3600) demonstrate that ViCLIP-OT consistently outperforms CLIP and SigLIP baselines in both in-domain and zero-shot settings. HFEPX signals include Automatic Metrics with confidence 0.35. Updated from current HFEPX corpus.

Generated Mar 3, 2026, 7:56 PM · Grounded in abstract + metadata only

Key Takeaways

Extensive experiments on three Vietnamese benchmarks (UITOpenViIC, KTVIC, and Crossmodal-3600) demonstrate that ViCLIP-OT consistently outperforms CLIP and SigLIP baselines in…
On UIT-OpenViIC, the model achieves an average Recall@K of 67.34%, improving upon CLIP by 5.75 percentage points.

Researcher Actions

Treat this as method context, then pivot to protocol-specific HFEPX hubs.
Identify benchmark choices from full text before operationalizing conclusions.
Validate metric comparability (recall, recall@k).

Caveats

Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
Low-signal flag detected: protocol relevance may be indirect.

Recommended Queries

human-eval protocol design pairwise preference data quality inter-rater agreement adjudication

Research Summary

Contribution Summary

Extensive experiments on three Vietnamese benchmarks (UITOpenViIC, KTVIC, and Crossmodal-3600) demonstrate that ViCLIP-OT consistently outperforms CLIP and SigLIP baselines in both in-domain and zero-shot settings.
On UIT-OpenViIC, the model achieves an average Recall@K of 67.34%, improving upon CLIP by 5.75 percentage points.
In zero-shot evaluation on Crossmodal-3600, ViCLIPOT surpasses CLIP by 11.72 percentage points.

Why It Matters For Eval

Extensive experiments on three Vietnamese benchmarks (UITOpenViIC, KTVIC, and Crossmodal-3600) demonstrate that ViCLIP-OT consistently outperforms CLIP and SigLIP baselines in both in-domain and zero-shot settings.
In zero-shot evaluation on Crossmodal-3600, ViCLIPOT surpasses CLIP by 11.72 percentage points.

Researcher Checklist

Gap: Human feedback protocol is explicit

No explicit human feedback protocol detected.
Pass: Evaluation mode is explicit

Detected: Automatic Metrics
Gap: Quality control reporting appears

No calibration/adjudication/IAA control explicitly detected.
Gap: Benchmark or dataset anchors are present

No benchmark/dataset anchor extracted from abstract.
Pass: Metric reporting is present

Detected: recall, recall@k

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

pMoE: Prompting Diverse Experts Together Wins More in Visual Adaptation Category Neighbor

Citations: 0 Relevance: 3.65
- Shared arXiv category (cs.CV, cs.AI)
- Shared terminology (optimal)
Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving Category Neighbor

Citations: 0 Relevance: 3.20
- Shared arXiv category (cs.CV, cs.AI)
Spatio-Temporal Token Pruning for Efficient High-Resolution GUI Agents Category Neighbor

Citations: 0 Relevance: 3.20
- Shared arXiv category (cs.CV, cs.AI)
MoDora: Tree-Based Semi-Structured Document Analysis System Category Neighbor

Citations: 0 Relevance: 2.50
- Shared arXiv category (cs.AI)
- Shared terminology (first, retrieval)
Quantity Convergence, Quality Divergence: Disentangling Fluency and Accuracy in L2 Mandarin Prosody Category Neighbor

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.AI)
- Shared terminology (vietnamese)
Recycling Failures: Salvaging Exploration in RLVR via Fine-Grained Off-Policy Guidance Category Neighbor

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.AI)
- Shared terminology (first)
SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables Category Neighbor

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.AI)
- Shared terminology (first)
Terminology Rarity Predicts Catastrophic Failure in LLM Translation of Low-Resource Ancient Languages: Evidence from Ancient Greek Category Neighbor

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.AI)
- Shared terminology (first)

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote